Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.3717. Min Range: -14.3717
Max Act: 14.3717. Min Act: -0.1700
Data Index: 8150291 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.3717. Min Range: -14.3717
Max Act: 14.1842. Min Act: -0.1700
Data Index: 3975687 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.8717. Min Act: -0.1700
Data Index: 4654308 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.6217. Min Act: -0.1700
Data Index: 1378147 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.5592. Min Act: -0.1700
Data Index: 4649281 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.4967. Min Act: -0.1700
Data Index: 4071558 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.3092. Min Act: -0.1700
Data Index: 4603241 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.3717. Min Act: -0.1700
Data Index: 5133657 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.2467. Min Act: -0.1700
Data Index: 498790 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.3717. Min Range: -14.3717
Max Act: 13.2467. Min Act: -0.1700
Data Index: 5123545 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.8717. Min Act: -0.1700
Data Index: 4210035 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.8092. Min Act: -0.1700
Data Index: 1959585 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.8092. Min Act: -0.1700
Data Index: 1108894 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.8092. Min Act: -0.1700
Data Index: 6150195 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.8092. Min Act: -0.1700
Data Index: 583105 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.6842. Min Act: -0.1700
Data Index: 6057549 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.7467. Min Act: -0.1700
Data Index: 172246 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.7467. Min Act: -0.1700
Data Index: 1603850 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.7467. Min Act: -0.1700
Data Index: 8822355 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.3717. Min Range: -14.3717
Max Act: 12.6842. Min Act: -0.1700
Data Index: 2632713 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19